Browsing by Subject "Robotics"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Open Access
    Biologically inspired goal directed navigation for mobile robots
    (2016) Amayo, Paul Omondi; Verrinder, Robyn A
    This project involved an investigation into low-cost navigation of mobile robots with the aim of creating and adaptive navigation system inspired by behaviour seen in animals. The navigation module developed here would need to be able to successfully localise a robot and navigate it to a defined target. A critical literature review was carried out of current localisation and path-planning architectures and a bio-inspired approach using an Echo State Network and Liquid State Machine architecture was chosen as the base for the navigation modules. The navigation module implemented in this work is trained to navigate and localise itself in different environments drawing its inspiration from the behaviour of small rodents. These architectures were adapted for use by a robot with a view on the physical implementation of these architectures on an embedded low-cost robot using a Raspberry Pi computer. This robot was then built using low-cost, noisy proximity sensors which formed the inputs to the navigation modules. Before the deployment on the embedded robot the system was tested and validated in a full physics simulator. While the training of the Echo State Networks and Liquid State Machine has been carried out in the literature by the offline method of linear regression, in this work we introduce a novel way of training these networks that is online using concepts from adaptive filters. This online method increases the adaptability of this system while significantly decreasing its memory requirements making it very attractive for low-cost embedded robots. The end result from the project was a functioning navigation module using an Echo State Network that was able to navigate the robot to a target position as well as learn new paths, either using offline or online methods. The results showed that the Echo State Network approach was valid both in simulation and practically as a base for creating navigation modules for low-cost robots and could also lead to more efficient and adaptable robots being developed if the training was carried out in an online manner. The increased computational complexity of implementing the liquid State machine on analytical machines however made it unsuitable for deployment on robots using embedded micro-controllers.
  • Thumbnail Image
    Item
    Open Access
    The control of semi-autonomous robots
    (2004) McPhillips, Graeme; Tapson, Jonathan
    Robotic soccer is an international area of research which involves multiple robots collaborating in an adversarial and dynamic environment. Although many different forms gf robotic soccer are played, the University of Cape Town (UCT) chose the RoboCup small» sized robot league, officially known as the F180 RoboSoccer league, as a means of pursuing robotics research within the institution. The robot soccer game is played between two teams of ï¬ ve robots on a carpeted surface that is 2.8 m long by 2.3 m wide. The robots have their own on-board controllers that execute instructions sent to them from a computer-based artiï¬ cial intelligence (AI) system. In order for the AI system to keep track of all the robots and the ball (an orange golf ball), a global vision system is utilised. This global vision system uses images captured from either one or multiple digital cameras mounted above the ï¬ eld of play to determine the position and orientation of the team's robots, the position of the other teams' robots and ï¬ nally the position of the ball. In the true spirit of competition and furthering research, the rules which govern F180 RoboSoccer league cover only the basic format of the game thereby leaving various aspects of the robots, global vision system and AI design open for development. Since there was no RoboSoccer research in existence at UCT prior to the inception of this researcher's Masters' thesis the task included both the establishment of this format of robotics research at the institution as well as the actual design and development of the robots and the associated components as outlined below. Developing a team of robots requires a wide array of knowledge and the research undertaken was accordingly broken into three key components; the design of the robots (which included their related electronics and on-board controller), the design of a vision system and the design of an Al system. The main focus of this author's work was on the design of the robots as well as the overall structuring and integration of the UCT F180 RoboSoccer team. In addition, the areas of the global vision system and AI system that were covered within the scope of this thesis, are also presented. Prototypes were developed and in the ï¬ rst the main emphasis was placed on the movement of the robot, with the design of the kicking mechanism only occurring subsequent to this. After the ï¬ rst competition in 2002, this ï¬ rst design was abandoned in favour of developing a simpler robot with which to continue development. This simpler robot became the second prototype which, after testing, was reï¬ ned into the competition robot for 2003. During this period, the Al and global vision systems were developed by undergraduate thesis students. This research was then incorporated where applicable and, ï¬ nally, the residual problem areas were again addressed by a collaboration of staff and students. Whilst the design and implementation of the robots was very successful, the vision system was not successfully implemented before the competition in 2003. Although an autonomous game of soccer was not successfully played in the 2003 competition, the UCT F180 RoboSoccer team had made a great deal of progress towards this goal and, consequently, a strong foundation for future robotic soccer research within UCT has been established.
  • Thumbnail Image
    Item
    Open Access
    Design of a man-wearable control station for a robotic rescue system
    (2015) Fong, Wai K; Ginsberg, Samuel; Booysen, Tracy
    This report details the design, development, and testing of a man-wearable operator control station for the use of a low-cost robotic system in Urban Search and Rescue (USAR). The complete system, dubbed the "Scarab", is the 1st generation developed and built in the Robotics and Agents Research Laboratory (RARL) at the University of Cape Town (UCT), and was a joint effort between three MSc students. Robots have found a place in USAR as replaceable units which can be deployed into dangerous and confined voids in the place of humans. As such, they have been utilized in a large variety of disaster environments including ground, aerial, and underwater scenarios, and have been gathering research momentum since their first documented deployment in the rescue operations surrounding the 9/11 terrorist attacks. However one issue is their cost as they are not economical solutions, making them less viable for inclusion into a rescue mission as well as negatively affecting the operator‟s decisions in order to prioritise the safety of the unit. Another concern is their difficulty of transport, which becomes dependent on the size and portability of the robot. As such, the Scarab system was conceived to provide a deployable robotic platform which was lowcost, with a budget goal of US $ 500. To address the transportability concerns, it aimed to be portable and light-weight; being able to be thrown through a window by a single hand and withstanding a drop height of 3 m. It includes an internal sensor payload which incorporates an array of sensors and electronics, including temperature monitors and two cameras to provide both a normal and IR video feed. Two LED spotlights are used for navigation, and a microphone and buzzer is included for interaction with any discovered survivors. The operator station acts as the user interface between the operator and the robotic platform. It aimed to be as intuitive as possible, providing quick deployment and minimalizing the training time required for its operation. To further enhance the Scarab system‟s portability, it was designed to be a manwearable system, allowing the operator to carry the robotic platform on their back. It also acts as a charging station, supplying power to the robotic platform‟s on-board charging circuitry. The control station‟s mechanical chassis serves as the man-wearable component of the system, with the functionality being achieved by integration onto a tactical vest. This allows the operator to take the complete system on and off as a single unit without assistance, and uses two mounting brackets to dock the robotic platform. Key areas focussed upon during design were the weight and accessibility of the system, as well as providing a rugged housing for the internal electronics. All parts were manufactured in the UCT Mechanical Engineering workshop.
  • Thumbnail Image
    Item
    Open Access
    Development of cooperative behavioural model for autonomous multi-robots system deployed to underground mines
    (2015) Yinka-Banjo, Chika Ogochukwu; Bagula, Antoine; Osunmakinde, Isaac Olusegun
    The number of disasters that occur in underground mine environments monthly all over the world cannot be ignored. Some of these disasters for instance are roof-falls; explosions, toxic gas inhalation, in-mine vehicle accidents, etc. can cause fatalities and/or disabilities. However, when such accidents happen during mining operations, rescuers find it difficult to respond to it immediately. This creates the necessity to bridge the gap between the lives of miners and the product acquired from the underground mines by using multi-robot systems. This thesis proposes an autonomous multi-robot cooperative behavioural model that can help to guide multi-robots in pre-entry safety inspection of underground mines. A hybrid swarm intelligent model termed, QLACS, that is based on Q-Learning (QL) and the Ant Colony System (ACS) is proposed to achieve cooperative behaviour in a MRS. The intelligent model was developed by harnessing the strengths of both QL and ACS algorithms. The ACS is used to optimize the routes used for each robot while the QL algorithm is used to enhance cooperation among the autonomous robots. The communication within the QLACS model for cooperative behavioural purposes is varied. The performance of the algorithms in terms of communication was evaluated by using a simulation approach. An investigation is conducted on the evaluation/scalability of the model using the different numbers of robots. Simulation results show that the methods proposed in this thesis achieved cooperative behaviour among the robots better than state-of-the-art or other common approaches. Using time and memory consumption as performance metrics, the results reveal that the proposed model can guide two, three and up to four robots to achieve efficient cooperative inspection behaviour in underground terrains.
  • Thumbnail Image
    Item
    Open Access
    The dynamic modelling and development of a controller for a general purpose remotely operated underwater vehicle
    (2016) Finbow, Maximillian; Mouton, Hendrik Daniël
    A preliminary mathematical model for the UCT SEAHOG Remotely operated underwater vehicle (ROV) is developed, including estimation of the rigid body, hydrodynamic and hydrostatic properties of the robot. A single state thruster model is developed and verified according to real life test data. A closed-loop speed controller is developed for the thruster module using a standard PI scheme and is implemented on an MSP430 microcontroller using software fixed-point algorithms. The complete ROV system is simulated in Simulink® in an open-loop configuration to gain insight into the expected motion from the vehicle. Controllers for depth and heading holding are designed using standard PID linearized control methods with gain scheduling and are then assessed within the complete system in a simulation environment. In addition, upgrades and maintenance are performed on the Power Pod, light and camera modules. Redesign, manufacture and testing of the SEAHOG junction box is performed, including a design solution to connect the tether power and fibre-optic lines at the surface and on the ROV. An extensive overhaul of the SEAHOG GUI is performed, utilising multicore processing architecture in LabVIEW and resulting in a user-orientated interface capable of controlling and monitoring all existing system data from the robot.
  • Thumbnail Image
    Item
    Open Access
    Understanding the motions of the cheetah tail using robotics
    (2015) Patel, Amir; Braae, Martin
    The cheetah is capable of incredible feats of manoeuvrability. But, what is interesting about these manoeuvres is that they involve rapid swinging of the animal's lengthy tail. Despite this, very little is understood about the cheetah tail and its motion, with the common view being that it is "heavy" and possibly used as a "counter balance" or as a "rudder". In this dissertation, this subject is investigated by exploring the motions of the cheetah tail by means of mathematic al models, feedback control and novel robot platforms. Particularly, the motion in the roll axis is first investigated and it is determined that it assists stability of high speed turns. This is validated by modelling and experimental testing on a novel tailed robot, Dima I. Inspired by cheetah video observations, the tail motion in the pitch axis during rapid acceleration and braking manoeuvres is also investigated. Once again modelling and experimental testing on a tailed robot are performed and the tail is shown to stabilise rapid acceleration manoeuvres. Video observations also indicate the tail movement in the shape of a cone: a combination of pitching and yawing. Understanding this motion is done by setting up an optimization problem. Here, the optimal motion was found to be to a cone which results in a continuous torque on the body during a turn while galloping. A novel two degree of freedom tailed robot, Dima II, was then developed to experimentally validate the effect of this motion. Lastly, measurement of the cheetah tail inertia was performed during a routine necropsy where it was found to have lower inertia than assumed. However, the tail has thick, long fur that was tested in a wind tunnel. Here it was found that the furry tail is capable of producing significant drag forces without a weight penalty. Subsequently, mathematical models incorporating the aerodynamics of the tail were developed and these were used to demonstrate its effectiveness during manoeuvres.
  • Thumbnail Image
    Item
    Open Access
    Visual servo control on a humanoid robot
    (2015) Bombile, Michael Bosongo; Braae, Martin
    This thesis deals with the control of a humanoid robot based on visual servoing. It seeks to confer a degree of autonomy to the robot in the achievement of tasks such as reaching a desired position, tracking or/and grasping an object. The autonomy of humanoid robots is considered as crucial for the success of the numerous services that this kind of robots can render with their ability to associate dexterity and mobility in structured, unstructured or even hazardous environments. To achieve this objective, a humanoid robot is fully modeled and the control of its locomotion, conditioned by postural balance and gait stability, is studied. The presented approach is formulated to account for all the joints of the biped robot. As a way to conform the reference commands from visual servoing to the discrete locomotion mode of the robot, this study exploits a reactive omnidirectional walking pattern generator and a visual task Jacobian redefined with respect to a floating base on the humanoid robot, instead of the stance foot. The redundancy problem stemming from the high number of degrees of freedom coupled with the omnidirectional mobility of the robot is handled within the task priority framework, allowing thus to achieve con- figuration dependent sub-objectives such as improving the reachability, the manipulability and avoiding joint limits. Beyond a kinematic formulation of visual servoing, this thesis explores a dynamic visual approach and proposes two new visual servoing laws. Lyapunov theory is used first to prove the stability and convergence of the visual closed loop, then to derive a robust adaptive controller for the combined robot-vision dynamics, yielding thus an ultimate uniform bounded solution. Finally, all proposed schemes are validated in simulation and experimentally on the humanoid robot NAO.